Agriculture remains a cornerstone of global health and economic sustainability, yet labor-intensive tasks such as harvesting high-value crops continue to face growing workforce shortages. Robotic harvesting systems offer a promising solution; however, their deployment in unstructured orchard environments is constrained by inefficient perception-to-action pipelines. In particular, existing approaches often rely on exhaustive inverse kinematics or motion planning to determine whether a target fruit is reachable, leading to unnecessary computation and delayed decision-making. Our approach combines RGB-D perception with active learning to directly learn reachability as a binary decision problem. We then leverage active learning to selectively query the most informative samples for reachability labeling, significantly reducing annotation effort while maintaining high predictive accuracy. Extensive experiments demonstrate that the proposed framework achieves accurate reachability prediction with substantially fewer labeled samples, yielding approximately 6--8% higher accuracy than random sampling and enabling label-efficient adaptation to new orchard configurations. Among the evaluated strategies, entropy- and margin-based sampling outperform Query-by-Committee and standard uncertainty sampling in low-label regimes, while all strategies converge to comparable performance as the labeled set grows. These results highlight the effectiveness of active learning for task-level perception in agricultural robotics and position our approach as a scalable alternative to computation-heavy kinematic reachability analysis. Our code is available through https://github.com/wsu-cyber-security-lab-ai/active-learning.

翻译：农业仍是全球健康与经济可持续性的基石，然而诸如高价值作物采摘等劳动密集型任务正面临日益严重的劳动力短缺问题。机器人采摘系统提供了一种有前景的解决方案，但它们在非结构化果园环境中的部署受限于低效的感知-行动流水线。具体而言，现有方法往往依赖穷举式逆运动学或运动规划来判断目标水果是否可达，导致不必要的计算和决策延迟。我们的方法将RGB-D感知与主动学习相结合，直接将可达性学习为一个二分类决策问题。随后，我们利用主动学习选择性查询信息量最大的样本进行可达性标注，在保持高预测精度的同时大幅减少标注工作量。大量实验表明，所提出的框架能够以显著更少的标注样本实现准确的可达性预测，相比随机采样准确率提高约6-8%，并支持对新果园配置进行标签高效的适应性调整。在评估的策略中，基于熵和边界的采样在低标签场景下优于查询委员会和标准不确定性采样，而随着标注样本集的增长，所有策略收敛到相近的性能。这些结果突显了主动学习在农业机器人任务级感知中的有效性，并将我们的方法定位为计算密集型运动学可达性分析的可扩展替代方案。我们的代码可通过https://github.com/wsu-cyber-security-lab-ai/active-learning获取。